arXiv Machine Learning

Do Location Encoders Capture Spatial Effects? A GeoShapley Benchmark Across Scales

Location encoders transform geographic coordinates into high‑dimensional embeddings for machine learning, yet it is unclear how well these embeddings capture interpretable spatial effects. This study benchmarks GeoShapley—a game‑theoretic explainer treating all location features as a single joint player—against eleven TorchSpatial encoders on a synthetic process with known coefficients, across grid, county, and global scales, with and without raw coordinates and under different training regimes. The results show that primary coefficient recovery is consistently high across encoders, while secondary coefficient recovery varies more with scale, especially at the global level, and raw‑coordinate baselines remain competitive throughout.

arXiv Machine Learning
Sep 23

MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale

The paper introduces MIND, a method that distills specialist geospatial model embeddings into a single generalist coordinate embedding with adjustable spatial granularity, using nested supervision across multiple embedding dimensions. MIND’s design allows downstream predictors to use only leading chunks or apply a Chunked Penalty to downweight finer details without retraining the INR. The authors evaluate MIND on CoordBench, a large INR benchmark of 52 datasets and 78 targets, and report that MIND and its Chunked Penalty variant achieve the highest regression and classification scores, especially under regional holdout, establishing a new state‑of‑the‑art for geographic implicit neural representations.

By Isaac Corley, Arjun Rao, Esther Rolf, Konstantin Klemmer, Evan Shelhamer, Nils Lehmann, Marc Ru{\ss}wurm, Gengchen Mai, Nathan Jacobs, Hannah Kerner
arXiv Computer Vision
6d ago

X Marks the Spot: Diffusion for Image Geolocalization with Location Representations

The paper introduces a new diffusion-based approach for image geolocalization that learns in the pretrained representation space of location encoders rather than directly predicting coordinates. A Location Autoencoder (LAE) maps these embeddings back to coordinates with kilometer-level accuracy, enabling a latent diffusion model (DIG) to transport noise to location embeddings conditioned on image features. DIG outperforms previous coordinate-based generative models and sets a new state of the art on three major benchmarks, becoming the first generative model to surpass retrieval-based methods and improving retrieve‑and‑rerank systems when used as a prior.

By Brian Wei, Chih-Chuan Hsu, Tianyi Gao, Daniel Cher, Eric Xing, Danielle Beaulieu, Nathan Jacobs
arXiv Machine Learning
Oct 12

PlacePulse: Learning Transferable Place Representations from Structural Geographic Data

PlacePulse is a structural geospatial foundation model that transforms 572 attributes—expanded to 2,288 through H3 neighborhood aggregates—into 256‑dimensional unit‑norm embeddings for over a million H3 resolution‑7 cells across the United States. The model achieves high intrinsic reconstruction quality (mean $R^2 = 0.853$) and strong spatial organization (Moran's $I = 0.93$), while outperforming a dimensionality‑matched baseline on 74 held‑out targets from 12 external sources and competing with Google’s Population Dynamics Foundation Model on various health, economic, election, mobility, and social‑vulnerability outcomes. These results demonstrate that static structural composition can serve as a distinct and complementary modality for geospatial foundation models.

By Luc\'ia Garc\'ia-Duarte, Miguel \'Alvarez, Diego Vicente, Javier P\'erez Trufero, Javier de la Torre
arXiv AI
Aug 19

MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale

MoRA is a human‑centric geospatial representation learning framework that uses a large mobility graph as its backbone to fuse spatial tokenization, graph neural networks, and asymmetric contrastive learning. It aligns over 100 million points of interest, massive remote sensing imagery, and structured demographic data with a billion‑edge mobility graph, producing compact 128‑dimensional embeddings that capture socio‑economic context and functional roles of locations. On a benchmark of nine downstream social and economic prediction tasks, MoRA outperforms state‑of‑the‑art models by an average of 12.9% and demonstrates scaling behavior analogous to large language models.

By Ya Wen, Jixuan Cai, Qiyao Ma, Linyan Li, Xinhua Chen, Chris Webster, Yulun Zhou
arXiv Computer Vision
Oct 26

LoCA: Enabling Multi-Modality in Geospatial Location Encoders

arXiv:2610.32894v1 Announce Type: new Abstract: Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We pr...

By Panagiotis Koromilas, Eleanna Vali, Diogenis Antonopoulos, Eleni Saka, Dimitris Christofis, Nikolaos Ioannis Bountos, Konstantin Klemmer, Ioannis Papoutsis, Yannis Panagakis, Mihalis A. Nicolaou
arXiv Computer Vision
Oct 15

GeoThinker-$F$: Endogenous Predictive World Representations for Fast Spatial Intelligence

arXiv:2610.20592v1 Announce Type: new Abstract: Existing geometry-aware Multimodal Large Language Models (MLLMs) increasingly rely on external 3D encoders to provide structural priors, but executing...

By Haoyuan Li, Qihang Cao, Huanyuan Zhou, Xin Hu, Sijia Chen, Zihan Guo, Kun Xiang, Yunshuang Nie, Tao Tang, Xinlong Zheng, Jia-Wang Bian, Xianming Liu, Xiaodan Liang
arXiv Computer Vision
Aug 27

GTPred: Benchmarking MLLMs for Interpretable Geo-localization and Time-of-capture Prediction

GTPred is a new benchmark for geo‑temporal prediction that evaluates multi‑modal large language models (MLLMs) on 370 images taken across 120 years worldwide. It assesses predictions by matching both the year and a hierarchical location sequence, and includes annotated reasoning chains to test intermediate reasoning. Experiments on 15 MLLMs show that while visual perception is strong, models still lack world knowledge and geo‑temporal reasoning, and that adding temporal data improves location inference.

By Jinnao Li, Tingzhu Chen, Changbo Wang
arXiv AI
Aug 10

SLED: Scalable Location Encoding via Distillation

arXiv:2608. 06612v1 Announce Type: cross Abstract: The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer size of the Earth Observations (EO), differing modalities, and different sensor types pose significant challenges in doing so.

By Kevin Lane, Zhongying Wang, Esther Rolf, Morteza Karimzadeh